Aaron Portnoy

Head of Research & Innovation

Aaron has more than twenty years building and leading research programs and early-stage cybersecurity companies at the intersection of offensive security, exploit economics, and AI security. He designed and directed the first six Pwn2Own competitions while running the Zero Day Initiative. He also co-founded security companies and was appointed the inaugural “Hacker-in-Residence” and later “Hacker Fellow” at Dartmouth College. Profiled on the cover of TIME magazine in a feature about zero-day vulnerabilities and exploit markets, he has presented research at more than thirty global venues. At Mindgard, he leads the Research & Development team integrating cutting-edge red team methodologies into the Mindgard product.

Author's Work

TheLibrarian.io's AI Security Is Checked Out, and Their Disclosure Response Is Overdue

The Mindgard platform identified high severity vulnerabilities in TheLibrarian.io platform

Zed IDE Vulnerabilities & Coordinated Disclosure

The Mindgard solution identified two vulnerabilities in the Zed IDE and our team worked with the developers on a coordinated remediation process.

Inside OpenAI Sora 2: Uncovering System Prompts Driving Multi-Modal LLMs

We show how we revealed Sora 2's system prompt by experimenting across multiple modalities, including text-to-image, ASCII and glyph renderings, video, audio captions, and transcripts.

From Prompt to Pwn: Cline Bot AI Coding Agent Vulnerabilities

In this post, we’ll show how a clever attacker can slip prompt injections into source files, turning a helpful partner into a hazard.

Forced Descent: Google Antigravity Persistent Code Execution Vulnerability

Mindgard identified a flaw in Google's Antigravity IDE that shows how traditional trust assumptions break down in AI-driven software.

Mindgard, the leading provider of Artificial Intelligence security solutions, helps enterprises secure their AI models, agents, and systems across the entire lifecycle. Mindgard’s solution uncovers shadow AI, conducts automated AI red teaming by emulating adversaries, and delivers runtime protection against attacks like prompt injection and agentic manipulation. Trusted by leading organizations in finance, healthcare, and technology, Mindgard is backed by investors including .406 Ventures, IQ Capital, Atlantic Bridge, and Lakestar.